Itza Hernandez-Sequeira, Ruben Fernandez-Beltran, Yonghao Xu, Pedram Ghamisi, and Filiberto Pla
Deep semi-supervised learning (DSSL) is a rapidly-growing field that takes advantage of a limited number of labeled examples to leverage massive amounts of unlabeled data. The underlying idea is that training on small yet well-selected examples can perform as effectively as a predictor trained on a larger number chosen at random. In this study, we explore the most relevant approaches in DSSL literature like FixMatch, CoMatch, and, the class aware contrastive SSL (CCSSL) . Our objective is to perform an initial comparative study of these methods and assess them on two remote sensing (RS) datasets: UCM and AID. The performance of these methods was determined based on their accuracy in comparison to a supervised benchmark. The results highlight that the CoMatch framework achieves the highest accuracy for both the UCM and AID datasets, with accuracies of 95.52% and 93.88% respectively. Importantly, all DSSL algorithms outperform the supervised benchmark, emphasizing their effectiveness in leveraging a limited number of labeled examples to enhance classification accuracy for remote sensing scene classification tasks. The code used in this study was adapted from CCSSL and the detailed implementation will be available on GitHub.
International Conference on Image Analysis and Processing, 463-474, 2023-09-05.